Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to opposition or resistance

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating opposition or resistance to authority or policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tesy
    -0.76
    ahime
    -0.75
    okes
    -0.72
    esi
    -0.71
    nces
    -0.70
    illin
    -0.69
    reau
    -0.68
    efficients
    -0.67
    urga
    -0.66
    ebus
    -0.66
    POSITIVE LOGITS
     perfection
    0.81
     minimize
    0.75
     preserve
    0.74
     maximize
    0.71
     defend
    0.71
     conserve
    0.69
     communism
    0.69
     oppose
    0.69
     whom
    0.67
     conform
    0.67
    Act Density 0.180%

    No Known Activations